decision-mapping

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to process user-supplied Markdown files ('Decision Maps') to direct agent behavior, which creates a potential surface for indirect prompt injection.
  • Ingestion points: In SKILL.md, the 'Resume' section explicitly instructs the agent to 'Load the whole map as context' for the session.
  • Boundary markers: The instructions do not provide explicit delimiters or guidance for the agent to distinguish between planning data and potentially malicious instructions embedded within the decision map file.
  • Capability inventory: The skill directs the agent to execute actions based on map content, including invoking tools like the /prototype skill which may have file system or code execution capabilities.
  • Sanitization: There is no mention of sanitizing or validating the content of the Markdown file before it is incorporated into the session context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 05:56 PM
Security Audit — agent-trust-hub — decision-mapping